Explains the standard Mini Infra workflow and which skill to reach for at each step — brainstorm → plan → execute → review → ship — plus the worktree and diagnostic helpers that wrap around it. Use this skill whenever the user asks "what's the workflow", "which skill do I use for X", "how do I work on a feature/task", "what skills do I have", "remind me of the flow", "help me with skills", "what's next", "where am I in the process", or any equivalent ask for a workflow refresher or a pointer to the right skill. Also use it when the user is mid-flow and seems unsure which skill comes next (e.g. they just finished a review and ask "now what?"). Do not trigger for questions about Claude Code itself (slash commands, hooks, MCP) — those go to claude-code-guide — and do not trigger when the user has already named the specific skill they want to run.
EnglishFinds the largest TypeScript files in the Mini Infra codebase, helps the user pick one, explores how it's wired into the rest of the app, proposes a DRY refactor strategy, implements the refactor, and writes focused unit tests for the new abstractions. Use this skill whenever the user wants to find files to refactor, clean up a large file, improve DRY/maintainability, or reduce duplication — even if they don't name a specific file. Trigger on: "refactor a large file", "clean up our biggest files", "DRY up this file", "what files should we refactor", "find files to refactor", "our biggest files", "top files by line count", "this file is too big", "split this file", "improve maintainability", or when the user mentions a 1000+ line file and wants it improved.
EnglishIncludes Help Skills and Refactor Large File.
Supported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Help Skills
Explains the standard Mini Infra workflow and which skill to reach for at each step — brainstorm → plan → execute → review → ship — plus the worktree and diagnostic helpers that wrap around it. Use this skill whenever the user asks "what's the workflow", "which skill do I use for X", "how do I work on a feature/task", "what skills do I have", "remind me of the flow", "help me with skills", "what's next", "where am I in the process", or any equivalent ask for a workflow refresher or a pointer to the right skill. Also use it when the user is mid-flow and seems unsure which skill comes next (e.g. they just finished a review and ask "now what?"). Do not trigger for questions about Claude Code itself (slash commands, hooks, MCP) — those go to claude-code-guide — and do not trigger when the user has already named the specific skill they want to run.
Refactor Large File
Finds the largest TypeScript files in the Mini Infra codebase, helps the user pick one, explores how it's wired into the rest of the app, proposes a DRY refactor strategy, implements the refactor, and writes focused unit tests for the new abstractions. Use this skill whenever the user wants to find files to refactor, clean up a large file, improve DRY/maintainability, or reduce duplication — even if they don't name a specific file. Trigger on: "refactor a large file", "clean up our biggest files", "DRY up this file", "what files should we refactor", "find files to refactor", "our biggest files", "top files by line count", "this file is too big", "split this file", "improve maintainability", or when the user mentions a 1000+ line file and wants it improved.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Help Skills skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.